API Reference

Public developer API reference for AICredits endpoints — chat completions, responses, images, audio, embeddings, models, credits, and health checks.

Base URL: https://api.aicredits.in

LLM endpoints use the /v1/ prefix and are OpenAI-compatible. Public platform metadata endpoints use /api/.

Endpoint Matrix

Area	Method	Path	Auth	Notes
Chat	`POST`	`/v1/chat/completions`	API key	OpenAI-compatible chat completions, including streaming and tools
Responses	`POST`	`/v1/responses`	API key	OpenAI-compatible responses endpoint where supported
Images	`POST`	`/v1/images/generations`	API key	Text-to-image generation
Audio	`POST`	`/v1/audio/speech`	API key	Text-to-speech generation
Audio	`POST`	`/v1/audio/transcriptions`	API key	Speech-to-text transcription
Embeddings	`POST`	`/v1/embeddings`	API key	Vector embeddings
Credits	`GET`	`/v1/credits`	API key	Current API-key wallet balance
Models	`GET`	`/api/models`	Public	Public model catalog
Health	`GET`	`/health`	Public	Basic service health
Health	`GET`	`/health/ready`	Public	Dependency readiness

Authentication

All endpoints except GET /api/models and GET /health require a Bearer token:

Authorization: Bearer sk-your-key-here

API keys are created in Dashboard → API Keys. Keys follow the format sk-{64 hex chars}.

Dashboard session APIs are intentionally not part of the public developer API contract. Use the dashboard UI for sign-in, wallet top-ups, billing history, and API-key management.

Chat Completions

POST /v1/chat/completions

The core LLM proxy endpoint. OpenAI-compatible — works with any OpenAI SDK.

Request body:

Field	Type	Required	Description
`model`	string	Yes	Model ID, e.g. `openai/gpt-4o-mini` or `anthropic/claude-sonnet-4.6`
`messages`	array	Yes	Array of `{role, content}` objects
`stream`	boolean	No	Enable SSE streaming (default: false)
`temperature`	number	No	0–2, controls randomness
`max_tokens`	integer	No	Maximum tokens to generate
`response_format`	object	No	`{"type": "json_object"}` for JSON mode
`tools`	array	No	Function definitions for tool calling
`tool_choice`	string/object	No	`"auto"`, `"none"`, `"required"`, or specific tool
`cache`	boolean	No	Enable prompt caching for Claude models
`no_cache`	boolean	No	Bypass semantic cache for this request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aicredits.in/v1",
    api_key="sk-your-key-here",
)

response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.aicredits.in/v1",
  apiKey: "sk-your-key-here",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);

curl https://api.aicredits.in/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Response:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1709123456,
  "model": "gpt-4o-mini",
  "choices": [{
    "index": 0,
    "message": { "role": "assistant", "content": "Hello! How can I help you?" },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 19,
    "completion_tokens": 9,
    "total_tokens": 28
  }
}

Image Generation

POST /v1/images/generations

Generate images from text prompts. Compatible with the OpenAI Images API.

Request body:

Field	Type	Required	Description
`model`	string	No	`dall-e-3` (default) or `dall-e-2`
`prompt`	string	Yes	Text description (max 4000 chars for DALL-E 3)
`n`	integer	No	Number of images (DALL-E 3: max 1)
`size`	string	No	`1024x1024`, `1792x1024`, or `1024x1792`
`quality`	string	No	`standard` or `hd`
`response_format`	string	No	`url` (default) or `b64_json`

curl https://api.aicredits.in/v1/images/generations \
  -H "Authorization: Bearer sk-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A serene view of the Himalayas at sunrise",
    "size": "1024x1024"
  }'

Text-to-Speech

POST /v1/audio/speech

Convert text to speech. Returns raw audio bytes.

Request body:

Field	Type	Required	Description
`model`	string	Yes	`openai/tts-1`, `openai/tts-1-hd`, or `sarvam/bulbul-v2`
`input`	string	Yes	Text to synthesize (max 4096 chars)
`voice`	string	Yes	`alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`
`response_format`	string	No	`mp3` (default), `opus`, `aac`, `flac`

Transcription

POST /v1/audio/transcriptions

Transcribe audio to text.

Request body:

Field	Type	Required	Description
`model`	string	Yes	`openai/whisper-1` or `sarvam/saarika-v2`
`input_audio.data`	string	Yes	Base64-encoded audio
`input_audio.format`	string	Yes	`mp3`, `wav`, `m4a`, `webm`, etc.
`language`	string	No	ISO-639-1 code, auto-detected if omitted

Embeddings

POST /v1/embeddings

Generate vector embeddings for text.

Request body:

Field	Type	Required	Description
`model`	string	Yes	e.g. `openai/text-embedding-3-small`
`input`	string or array	Yes	Text(s) to embed

curl https://api.aicredits.in/v1/embeddings \
  -H "Authorization: Bearer sk-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/text-embedding-3-small",
    "input": "The quick brown fox"
  }'

Models

GET /api/models

List all available models. No authentication required.

curl https://api.aicredits.in/api/models

Response:

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-4o-mini",
      "name": "GPT-4o Mini",
      "provider": "openai",
      "context_window": 128000,
      "input_cost_per_1m": 0.15,
      "output_cost_per_1m": 0.60
    }
  ]
}

Health

GET /health

Returns {"status": "ok"}. No authentication required. Used for uptime monitoring.

GET /health/ready

Returns {"status": "ready", "db": "ok", "redis": "ok"} when all dependencies are healthy.

Error Format

All errors follow the same structure:

{
  "error": {
    "message": "Human-readable description",
    "type": "error_type",
    "code": 400
  }
}

See Error Handling → for the full error code reference and retry guidance.

The credit balance check (GET /v1/credits) returns your current API-key wallet balance in INR with Bearer token authentication.

On this page